GLake: optimizing GPU memory management and IO transmission.

FlagScale is a large model toolkit based on open-sourced projects.

Universal model exchange and serialization format for decision tree forests

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

This is a code repository for pytorch c++ (or libtorch) tutorial.

A toolkit for making real world machine learning and data analysis applications in C++

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

Model optimizer used in Adlik.

A light weight configuration library for C++

Adlik: Toolkit for Accelerating Deep Learning Inference

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

OpenMMLab Detection Toolbox and Benchmark

Pytorch 中文文档

Vitis_Accel_Examples

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

2023年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

A large scale video database for violence detection, which has 2,000 video clips containing violent or non-violent behaviours.

Python - 100天从新手到大师

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.